acryl-datahub 1.2.0.9rc1__py3-none-any.whl → 1.2.0.9rc2__py3-none-any.whl

{acryl_datahub-1.2.0.9rc1.dist-info → acryl_datahub-1.2.0.9rc2.dist-info}/RECORD

@@ -1,7 +1,7 @@
-acryl_datahub-1.2.0.9rc1.dist-info/licenses/LICENSE,sha256=9xNHpsD0uYF5ONzXsKDCuHHB-xbiCrSbueWXqrTNsxk,11365
+acryl_datahub-1.2.0.9rc2.dist-info/licenses/LICENSE,sha256=9xNHpsD0uYF5ONzXsKDCuHHB-xbiCrSbueWXqrTNsxk,11365
 datahub/__init__.py,sha256=aq_i5lVREmoLfYIqcx_pEQicO855YlhD19tWc1eZZNI,59
 datahub/__main__.py,sha256=pegIvQ9hzK7IhqVeUi1MeADSZ2QlP-D3K0OQdEg55RU,106
-datahub/_version.py,sha256=_H3eOOLcAfSj64l30V-SpArSKBd8L7socBTn4sC-zB0,323
+datahub/_version.py,sha256=czL9t4OxwP0dn-BD3TMnolCh7B9D-oNG5I9JL0ME8FI,323
 datahub/entrypoints.py,sha256=9Qf-37rNnTzbGlx8S75OCDazIclFp6zWNcCEL1zCZto,9015
 datahub/errors.py,sha256=p5rFAdAGVCk4Lqolol1YvthceadUSwpaCxLXRcyCCFQ,676
 datahub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -267,8 +267,8 @@ datahub/ingestion/source/bigquery_v2/bigquery_helper.py,sha256=QER3gY8e_k1_eNVj7
 datahub/ingestion/source/bigquery_v2/bigquery_platform_resource_helper.py,sha256=9_sfX8BE2vt9RjBMyq27UxCxBaSlD5o3L4gQxrwlPvA,4961
 datahub/ingestion/source/bigquery_v2/bigquery_queries.py,sha256=2syDMaRpYEbtGUVejVAK5d6g8HqM54ZyEM908uLJ55o,3393
 datahub/ingestion/source/bigquery_v2/bigquery_report.py,sha256=v7_zkZzymKPmZKWAxnxmvmHC-8TQVGHUT-pBQFNehqc,7962
-datahub/ingestion/source/bigquery_v2/bigquery_schema.py,sha256=DHw5Z_rxj_fR09p7SO0UmDdvYEa_ViIRnLE9CFxPAAk,32525
-datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py,sha256=29E_25jLpMIgWcYRC0ZcYd1fvaFtSi2T8S6hSwiTDTY,51090
+datahub/ingestion/source/bigquery_v2/bigquery_schema.py,sha256=zbYb1EYnCJxgvsU8oT_76l0q_BW1exVjMWM1GAgd1nc,32600
+datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py,sha256=c9a-SlZDOYNiS__vC5ezVVNM0UHasXWxWNRZkkP_aOo,51552
 datahub/ingestion/source/bigquery_v2/bigquery_test_connection.py,sha256=cATxwi5IPzj3BldRRAVcLqzSFmmYEPvqa7U0RFJbaAc,7645
 datahub/ingestion/source/bigquery_v2/common.py,sha256=IinOy-RO4UZGxSf5scaN02672BzZuNsjJZ56axti6iI,4016
 datahub/ingestion/source/bigquery_v2/lineage.py,sha256=jju14mJbAUMA_K3j2yq-TdZV202cjd5rBAsDPJGEVno,44900
@@ -1114,8 +1114,8 @@ datahub_provider/operators/datahub_assertion_operator.py,sha256=uvTQ-jk2F0sbqqxp
 datahub_provider/operators/datahub_assertion_sensor.py,sha256=lCBj_3x1cf5GMNpHdfkpHuyHfVxsm6ff5x2Z5iizcAo,140
 datahub_provider/operators/datahub_operation_operator.py,sha256=aevDp2FzX7FxGlXrR0khoHNbxbhKR2qPEX5e8O2Jyzw,174
 datahub_provider/operators/datahub_operation_sensor.py,sha256=8fcdVBCEPgqy1etTXgLoiHoJrRt_nzFZQMdSzHqSG7M,168
-acryl_datahub-1.2.0.9rc1.dist-info/METADATA,sha256=b0i8DTQvhz0wjm4LlnQ4cAEB3Fzj4VWzmznolB87FoU,186907
-acryl_datahub-1.2.0.9rc1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-acryl_datahub-1.2.0.9rc1.dist-info/entry_points.txt,sha256=qopCAD6qrsijaZ9mTw3UlPCKsE00C3t9MbkkWow7pi4,9943
-acryl_datahub-1.2.0.9rc1.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
-acryl_datahub-1.2.0.9rc1.dist-info/RECORD,,
+acryl_datahub-1.2.0.9rc2.dist-info/METADATA,sha256=gQoHdltvvyFIK3SgD-5zF_BTJGyiAKWM7rcfqN4ZTy4,186875
+acryl_datahub-1.2.0.9rc2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+acryl_datahub-1.2.0.9rc2.dist-info/entry_points.txt,sha256=qopCAD6qrsijaZ9mTw3UlPCKsE00C3t9MbkkWow7pi4,9943
+acryl_datahub-1.2.0.9rc2.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
+acryl_datahub-1.2.0.9rc2.dist-info/RECORD,,

datahub/_version.py

@@ -1,6 +1,6 @@
 # Published at https://pypi.org/project/acryl-datahub/.
 __package_name__ = "acryl-datahub"
-__version__ = "1.2.0.9rc1"
+__version__ = "1.2.0.9rc2"
 
 
 def is_dev_mode() -> bool:

datahub/ingestion/source/bigquery_v2/bigquery_schema.py

@@ -283,23 +283,30 @@ class BigQuerySchemaApi:
         with self.report.list_datasets_timer:
             self.report.num_list_datasets_api_requests += 1
             datasets = self.bq_client.list_datasets(project_id, max_results=maxResults)
-            return [
-                BigqueryDataset(
-                    name=d.dataset_id,
-                    labels=d.labels,
-                    location=(
-                        d._properties.get("location")
-                        if hasattr(d, "_properties") and isinstance(d._properties, dict)
-                        else None
-                    ),
-                    # TODO: Fetch dataset description individually impacts overall performance if the number of datasets is high (hundreds); instead we should fetch in batch for all datasets.
-                    # TODO: Given we are calling get_dataset for each dataset, we may consume and publish other fields too, such as created, modified, etc...
-                    # https://cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.client.Client#google_cloud_bigquery_client_Client_get_dataset
-                    # https://cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.dataset.Dataset
-                    comment=self.bq_client.get_dataset(d.reference).description,
+            result = []
+            for d in datasets:
+                # TODO: Fetch dataset description individually impacts overall performance if the number of datasets is high (hundreds); instead we should fetch in batch for all datasets.
+                # https://cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.client.Client#google_cloud_bigquery_client_Client_get_dataset
+                # https://cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.dataset.Dataset
+                dataset = self.bq_client.get_dataset(d.reference)
+
+                location = (
+                    d._properties.get("location")
+                    if hasattr(d, "_properties") and isinstance(d._properties, dict)
+                    else None
+                )
+
+                result.append(
+                    BigqueryDataset(
+                        name=d.dataset_id,
+                        labels=d.labels,
+                        location=location,
+                        comment=dataset.description,
+                        created=dataset.created,
+                        last_altered=dataset.modified,
+                    )
                 )
-                for d in datasets
-            ]
+            return result
 
     # This is not used anywhere
     def get_datasets_for_project_id_with_information_schema(

datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py

@@ -12,6 +12,7 @@ from datahub.emitter.mce_builder import (
     make_dataset_urn_with_platform_instance,
     make_schema_field_urn,
     make_tag_urn,
+    make_ts_millis,
 )
 from datahub.emitter.mcp import MetadataChangeProposalWrapper
 from datahub.emitter.mcp_builder import BigQueryDatasetKey, ContainerKey, ProjectIdKey
@@ -300,6 +301,8 @@ class BigQuerySchemaGenerator:
         description: Optional[str] = None,
         tags: Optional[Dict[str, str]] = None,
         extra_properties: Optional[Dict[str, str]] = None,
+        created: Optional[int] = None,
+        last_modified: Optional[int] = None,
     ) -> Iterable[MetadataWorkUnit]:
         schema_container_key = self.gen_dataset_key(project_id, dataset)
 
@@ -349,6 +352,8 @@ class BigQuerySchemaGenerator:
             ),
             tags=tags_joined,
             extra_properties=extra_properties,
+            created=created,
+            last_modified=last_modified,
         )
 
     def _process_project(
@@ -484,6 +489,12 @@ class BigQuerySchemaGenerator:
                     else None
                 ),
                 description=bigquery_dataset.comment,
+                created=make_ts_millis(bigquery_dataset.created)
+                if bigquery_dataset.created
+                else None,
+                last_modified=make_ts_millis(bigquery_dataset.last_altered)
+                if bigquery_dataset.last_altered
+                else None,
             )
 
         columns = None